Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 19848
    Prev
    Next
    INDEX
    Explanations

    mentions of a particular person's name with "ith" at the end

    oai_token-act-pair · gpt-3.5-turbo

    the recurring mention of a specific character or subject in historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¥µ
    -0.69
    tails
    -0.67
     Canaver
    -0.65
    detail
    -0.64
     Shelter
    -0.64
    patch
    -0.63
    berman
    -0.61
     lucky
    -0.60
    pees
    -0.60
    PDATE
    -0.59
    POSITIVE LOGITS
    otle
    0.99
    yll
    0.96
    reading
    0.85
    rones
    0.81
    iasis
    0.81
    iop
    0.81
    ith
    0.78
    ium
    0.78
    ttp
    0.75
    ofer
    0.74
    Activations Density 0.013%

    No Known Activations